# Evidence Synthesis for Decision Making in Healthcare

## Sutton, A. — Abrams, K. — Ades, A.

1ª Edición Mayo 2012

Inglés

Tapa dura

320 pags

1100 gr

x x cm

### ISBN 9780470061091

### Editorial JOHN WILEY & SONS

Recíbelo en un plazo De 7 a 10 días

### Description

In the evaluation of healthcare, rigorous methods of quantitative assessment are necessary to establish interventions that are beneficial, are superior to all alternatives and are cost-effective. Usually one study will not provide answers to these questions and it will be necessary to synthesize evidence from multiple sources. This book aims to outline a coherent approach to such evidence synthesis, for the purpose of decision making. Each chapter contains worked examples, exercises and solutions drawn from a variety of medical disciplines

Evidence Syntesis for Decision Making intends to provide a practical guide to the appropriate methods for synthesizing evidence for use in analytical decision models. More specifically, it proposes a comprehensive evidence synthesis framework, which models all the available data appropriately and efficiently in a format that can be incorporated directly into a decision model.

### Table of Contents

- Preface

**Introduction**- The rise of health economics
- Decision making under uncertainty
- Deterministic models
- Probabilistic decision modelling
- Evidence-based medicine
- Bayesian statistics
- NICE
- Structure of the book
- Summary key points
- Further reading
- References
**Bayesian methods and WinBUGS**- Introduction to Bayesian methods
- What is a Bayesian approach?
- Likelihood
- Bayes’ theorem and Bayesian updating
- Prior distributions
- Summarising the posterior distribution
- Prediction
- More realistic and complex models
- MCMC and Gibbs sampling
- Introduction to WinBUGS
- The BUGS language
- Graphical representation
- Running WinBUGS
- Assessing convergence in WinBUGS
- Statistical inference in WinBUGS
- Practical aspects of using WinBUGS
- Advantages and disadvantages of a Bayesian approach
- Summary key points
- Further reading
- Exercises
- References
**Introduction to decision models**- Introduction
- Decision tree models
- Model parameters
- Effects of interventions
- Quantities relating to the clinical epidemiology of the clinical condition being treated
- Utilities
- Resource use and costs
- Deterministic decision tree
- Stochastic decision tree
- Presenting the results of stochastic economic decision models 60
- Sources of evidence
- Principles of synthesis for decision models (motivation for the rest of the book)
- Summary key points
- Further reading
- Exercises
- References
**Meta-analysis using Bayesian methods**- Introduction
- Fixed Effect model
- Random Effects model
- The predictive distribution
- Prior specification for τ
- ‘Exact’ Random Effects model for Odds Ratios based on a Binomial likelihood
- Shrunken study level estimates
- Publication bias
- Study validity
- Summary key points
- Further reading
- Exercises
- References
**Exploring between study heterogeneity**- Introduction
- Random effects meta-regression models
- Generic random effect meta-regression model
- Random effects meta-regression model for Odds Ratio (OR) outcomes using a Binomial likelihood
- Autocorrelation and centring covariates
- Limitations of meta-regression
- Baseline risk
- Model for including baseline risk in a meta-regression on the (log) OR scale
- Final comments on including baseline risk as a covariate
- Summary key points
- Further reading
- Exercises
- References
**Model critique and evidence consistency in random effects meta-analysis**- Introduction
- The Random Effects model revisited
- Assessing model fit
- Deviance
- Residual deviance
- Model comparison
- Effective number of parameters, pD
- Deviance Information Criteria
- Exploring inconsistency
- Cross-validation
- Mixed predictive checks
- Summary key points
- Further reading
- Exercises
- References
**Evidence synthesis in a decision modelling framework**- Introduction
- Evaluation of decision models: One-stage vs two-stage approach
- Sensitivity analyses (of model inputs and model specifications)
- Summary key points
- Further reading
- Exercises
- References
**Multi-parameter evidence synthesis**- Introduction
- Prior and posterior simulation in a probabilistic model: Maple Syrup Urine Disease (MSUD)
- A model for prenatal HIV testing
- Model criticism in multi-parameter models
- Evidence-based policy
- Summary key points
- Further reading
- Exercises
- References
**Mixed and indirect treatment comparisons**- Why go beyond ‘direct’ head-to-head trials?
- A fixed treatment effects model for MTC
- Absolute treatment effects
- Relative treatment efficacy and ranking
- Random Effects MTC models
- Model choice and consistency of MTC evidence
- Techniques for presenting and understanding the results of MTC
- Multi-arm trials
- Assumptions made in mixed treatment comparisons
- Embedding an MTC within a cost-effectiveness analysis
- Extension to continuous, rate and other outcomes
- Summary key points
- Further reading
- Exercises
- References
**Markov models**- Introduction
- Continuous and discrete time Markov models
- Decision analysis with Markov models
- Evaluating Markov models
- Estimating transition parameters from a single study
- Likelihood
- Priors and posteriors for multinomial probabilities
- Propagating uncertainty in Markov parameters into a decision model
- Estimating transition parameters from a synthesis of several studies
- Challenges for meta-analysis of evidence on Markov transition parameters
- The relationship between probabilities and rates
- Modelling study effects
- Synthesis of studies reporting aggregate data
- Incorporating studies that provide event history data
- Reporting results from a Random Effects model
- Incorporating treatment effects
- Summary key points
- Further reading
- Exercises
- References
**Generalised evidence synthesis**- Introduction
- Deriving a prior distribution from observational evidence
- Bias allowance model for the observational data
- Hierarchical models for evidence from different study designs
- Discussion
- Summary key points
- Further reading
- Exercises
- References
**Expected value of information for research prioritisation and study design**- Introduction
- Expected value of perfect information
- Expected value of partial perfect information
- Computation
- Notes on EVPPI
- Expected value of sample information
- Computation
- Expected net benefit of sampling
- Summary key points
- Further reading
- Exercises
- References

**Appendix 1 Abbreviations****Appendix 2 Common distributions**- The Normal distribution
- The Binomial distribution
- The Multinomial distribution
- The Uniform distribution
- The Exponential distribution
- The Gamma distribution
- The Beta distribution
- The Dirichlet distribution
**Index**

**Tel**91 593 99 99

**Fax**91 448 21 88

**Dir**

C / Raimundo Lulio, 1, 28010 Madrid, España.

© 2021 Axón Librería S.L.

v1.53.0